© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 24998
    Prev
    Next
    INDEX
    Explanations

    math convergence (linear, Ricci, cyclic, matrices, Ramsey)

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    andom
    -0.08
    缴æİ¥æĪĸéĹ´æİ¥
    -0.07
    zeg
    -0.07
    æĺ¯ä¸Ģ大
    -0.07
    ancel
    -0.07
    <J
    -0.07
    è´¾
    -0.07
    edig
    -0.07
    æĺ¯ä¸ĢäºĽ
    -0.07
    èĭ¥å¹²
    -0.06
    POSITIVE LOGITS
    Lite
    0.07
    appy
    0.07
    _gender
    0.07
    ijn
    0.07
    óban
    0.07
    äºĮå¹´
    0.07
    оÑĩе
    0.07
    æĥħ人
    0.06
    ç¢İ
    0.06
    mdir
    0.06
    Activations Density 0.035%

    No Known Activations